Metraipolis › archive › dc_2bfa0119d0fe

H2Table: Hierarchical Hypergraph-Enhanced Large Language Models for Complex Table Reasoning — arXiv:2609.01216

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.01216
License (as archived)
CC0-1.0
Archived
2026-10-17T06:32:22.179Z
SHA-256 of the archived text
6ee0ae326dc306dcc4e614d7267a0dd82b9bcbe4eb0e37c60df1cb2d0ed032b5
Stable URL of this page
https://metraipolis.com/documento/dc_2bfa0119d0fe

How to cite

H2Table: Hierarchical Hypergraph-Enhanced Large Language Models for Complex Table Reasoning — arXiv:2609.01216 — arXiv (en), https://arxiv.org/abs/2609.01216 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2bfa0119d0fe (Metraipolis archive dc_2bfa0119d0fe, sha256 6ee0ae326dc306dcc4e614d7267a0dd82b9bcbe4eb0e37c60df1cb2d0ed032b5)
BibTeX
@misc{dc2bfa0119d0fe,
  title = {H2Table: Hierarchical Hypergraph-Enhanced Large Language Models for Complex Table Reasoning — arXiv:2609.01216},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01216},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2bfa0119d0fe; sha256 6ee0ae326dc306dcc4e614d7267a0dd82b9bcbe4eb0e37c60df1cb2d0ed032b5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01216. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tables are ubiquitous across diverse domains, yet reasoning over them remains a significant challenge for modern large language models (LLMs). Current approaches typically linearize tables into sequences, inherently overlooking their intrinsic two-dimensional and hierarchical structure. To address this, we propose H2Table (Hierarchical Hypergraph-Enhanced Table Reasoning), a novel framework that represents complex tables as hierarchical nested hypergraphs. To process this representation, we design a tailored hypergraph encoder to facilitate message passing between hyperedges (headers) and nodes (cells), thereby perceiving the semantic entailment relationships between them within complex tables. Furthermore, we introduce a set of learnable query vectors acting as a lightweight bridge to extract representative structural embeddings from the encoder into the LLM. Experimental results demonstrate that our approach effectively handles complex table question answering tasks with hierarchical nested headers. Notably, on the HiTab dataset, H2Table achieves an average improvement of 22.88% over state-of-the-art baselines on highly complex tables with a nesting depth of four. Our code is available at: this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.01216 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T06:15:12.680Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).